© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    can be

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is strongly activated by numeric tokens (especially floating‐point or other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kunna
    0.92
    е
    0.90
    ี
    0.84
    ir
    0.83
    ্
    0.83
    ف
    0.81
    ä
    0.80
     '
    0.74
    า
    0.73
    ifying
    0.72
    POSITIVE LOGITS
     distinguishes
    0.81
     approximates
    0.80
     DATA
    0.80
     conund
    0.79
    йдз
    0.79
    killers
    0.78
     contradicts
    0.77
    κτήθηκε
    0.77
     unlocks
    0.76
     tongs
    0.76
    Activations Density 0.059%

    No Known Activations